We are seeking a Senior Python Engineer (Agentic AI) to build and maintain production-ready services that orchestrate LLM agents across distributed environments. This role focuses on multi-agent communication and delegation using the A2A protocol, asynchronous processing, and streaming APIs that deliver results incrementally. The ideal candidate combines hands-on experience with multi-agent architectures and Python's asynchronous capabilities with expertise in LLM integrations, observability, containerization, and secure service-to-service communication.
Key Responsibilities
- Build and maintain Python services that orchestrate LLM agents, including routing and delegation across multiple agents.
- Implement agent-to-agent communication using the A2A protocol and agent cards.
- Develop streaming APIs that deliver results to users incrementally.
- Integrate LLMs through platforms such as AWS Bedrock/Anthropic and Azure OpenAI, using tool calling and prompt templates.
- Implement observability and LLM tracing, troubleshooting issues across distributed environments.
- Package and deploy services in containers and Kubernetes clusters.
- Secure service-to-service communication using mTLS and manage certificate lifecycles.
- Contribute to CI/CD pipelines and version control best practices.
What we'd like to see in a candidate:
- Strong Python development skills.
- Solid experience with asyncio, including async generators, queues, concurrent producers, and task cancellation.
- Experience building streaming APIs that return results incrementally.
- Familiarity with agentic frameworks such as Pydantic AI, LangGraph, or comparable tools.
- Experience with tool calling, agent routing, and prompt templating using Jinja2.
- Experience integrating LLM APIs through AWS Bedrock/Anthropic, Azure OpenAI, or comparable platforms.
- Experience with observability using OpenTelemetry and LLM tracing tools such as Arize Phoenix or comparable solutions.
- Ability to debug logs across multiple pods using Splunk, Datadog, or similar tools.
- Experience with Docker, including multi-stage builds, private registries, and devcontainers.
- Hands-on experience with Kubernetes deployments, services, ingress, probes, kubectl, and k9s.
- Experience using mTLS as a client and managing certificate lifecycles.
- Familiarity with Git and GitHub Actions.
- Excellent communication skills and a high level of English proficiency.
Nice to Have
- Experience with Software Lifecycle (SLC) documentation, particularly in regulated environments.
- Background in pharmaceutical, healthcare, or life sciences projects.
- Proven hands-on experience with the A2A protocol and multi-agent delegation.
Ambush is a people first company where talented, thoughtful individuals come together to build meaningful products and lasting partnerships. We believe the best work happens when people feel supported, trusted and empowered to bring their full abilities to the table.
Since 2015, because of our people first and long term mindset, we have grown into a partner relied on by some of the best companies in the world. We combine strong engineering, design and strategy with a growing strength in AI to help our clients see what is next and achieve bigger outcomes.
At the heart of everything we do is our team. We collaborate, take risks, lift each other up and take pride in doing work the right way, not settling for a quick makeshift solution. If you join Ambush, you join a group of people who want you to succeed and who show up for each other every day.
We believe in and expect real teamwork, a constant drive to be better, and delivering meaningful long term outcomes that we can be proud of together.